dsh-usage — security grade SAFE, quality 73/100

Security audit verdict: SAFE · quality 73/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by Aisland-SJL · Agent Tool · ★ 76

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is dsh-usage safe to install? View the security audit →

About dsh-usage

🌊 dsh-usage A persistent floating dock, a fully customizable balance / token-usage panel, an activity heatmap, and a dual-channel usage comparison for the DeepSeek Harness Web GUI (). ✨ Feature tour 🌊 Persistent dock Your key numbers stay visible at all times — balance glows green (red only when out of credit), rows are separated by hairlines, and a settings gear plus one-click refresh sit in the corner. When the sidebar collapses, the dock folds into a tiny balance pill. 🟢 Balance — green when healthy, red when drained 📊 Today / Month / Cache hit — glanceable token stats ⚙ Gear opens the panel · ↻ refresh re-queries instantly 🧲 Mirrors your pins — every change applies immediately 🎛️ Detail panel — all seven widgets A two-column card layout; every widget has a detail and a compact form, and can be drag-reordered, collapsed, hidden, or pinned. | 📊 Today

ai-toolsbalanceclaude-codedeepseekdeepseek-harnessdshdsh-plugintoken-usageusage-tracking

Quick Facts

Stars76
Forks10
LanguageJavaScript
CategoryAgent Tool
LicenseMIT
Quality Score73.4805572974174/100
Last Updated2026-08-31
Created2026-08-16
Platformsclaude-code, node
Est. Tokens~14k

dsh-usage alternative? Top 6 similar tools

Looking for a dsh-usage alternative? If you're comparing dsh-usage with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • cetus by drewnekota · ⭐ 146

    One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher

  • Tokdash by JingbiaoMei · ⭐ 79

    Agent Dashboard: Visualization and analytics for Sessions and Quota Usage. Track, analyze, and optimize token

  • claude-code-usage-bar by leeguooooo · ⭐ 374

    Lightweight Claude Code statusLine: 5h/7d rate-limit usage, reset countdowns, model + context window, prompt-c

  • tingly-box by tingly-dev · ⭐ 348

    Your Intelligence, Orchestrated. Every builder. Every team. Every agent. For Everyone.

  • pawwork by Astro-Han · ⭐ 196

    PawWork — free, open-source desktop AI agent for macOS and Windows, built on DeepSeek Harness (DSH). Free mode

  • toktrack by mag123c · ⭐ 190

    Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is dsh-usage?

dsh-usage is 🌊 Persistent dock & fully-customizable balance/usage panel for DeepSeek Harness — activity heatmap, dual-channel comparison, local-only & privacy-first. It is categorized as a Agent Tool with 76 GitHub stars.

What programming language is dsh-usage written in?

dsh-usage is primarily written in JavaScript. It covers topics such as ai-tools, balance, claude-code.

How do I install or use dsh-usage?

You can find installation instructions and usage details in the dsh-usage GitHub repository at github.com/Aisland-SJL/dsh-usage. The project has 76 stars and 10 forks, indicating an active community.

What license does dsh-usage use?

dsh-usage is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to dsh-usage?

The top alternatives to dsh-usage on Agent Skills Hub include cetus, Tokdash, claude-code-usage-bar. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools